First-In-Human Study Of A Novel Drug Discovered Using An AI Platform Has Begun In Hong Kong

Article  Dec   HK

The first healthy volunteer has been dosed in a first-in-human microdose trial of ISM001-055, according to an end-to-end artificial intelligence (AI)-driven drug discovery business. ISM001-055 is a small molecule inhibitor of a novel biological target identified by Pharma that has the potential to be a first-in-class inhibitor. AI, the company’s AI-powered drug discovery platform from start to finish. It’s being developed to treat idiopathic pulmonary fibrosis (IPF), a chronic lung disease that causes a gradual and permanent loss of lung function.

The business has started a micro-dose experiment to characterize the pharmacokinetic characteristics in people after completing IND-enabling investigations. The research is being undertaken in Australia, with healthy volunteers receiving ISM001-055 intravenously. ISM001-055 has shown promise in a variety of preclinical studies, including in vitro biological studies, pharmacokinetic studies, and safety studies. Myofibroblast activation, which contributes to the development of fibrosis, was greatly improved by the chemical. The unique target of ISM001-055 could be useful in a variety of fibrotic conditions.


The company’s CSO expressed his delight at the first antifibrotic medication candidate entering clinical trials. Because the drug candidate is now the first-ever AI-discovered novel chemical-based on an AI-discovered novel target, this is a significant milestone in the history of AI-powered drug development. The business has used its end-to-end AI-powered drug development platform, which includes generative biology and generative chemistry, to find new biological targets and create novel compounds with drug-like properties. ISM001-055 is the first of these compounds to enter clinical trials, and we anticipate others in the near future.


With the release of the Generative Tensorial Reinforcement Learning (GENTRL) system for a well-known target in record time, the business has previously shown its potential to manufacture drug-like hit molecules using AI. It also provided proof of concept for the target by using deep learning algorithms to identify new biological targets. These target discovery and generative chemistry capabilities were coupled in this unique antifibrotic therapy. Insilico Medicine performed the whole discovery process in 18 months, from target identification to preclinical candidate nomination, on a $2.6 million budget.


There are rare examples of a pharmaceutical business discovering a new target for a wide range of diseases, creating a novel chemical, and commencing human clinical trials, according to the company’s founder and CEO. To his knowledge, no one has ever done it using AI before. Preclinical target identification failure rates are quite high, and even after targets have been verified in animal models, more than half of Phase 2 clinical trials fail to owe to target selection. The pharmaceutical industry’s underlying great challenge is target discovery. With ISM001-055, we employed end-to-end AI to assess activity and safety in multiple preclinical models by connecting biology and chemistry.


The business will publicly unveil a portion of its Artificial Intelligence (AI) platform in September 2020, which is meant to help pharmaceutical target and drug discovery pipelines. Without any prior knowledge of computational biology or bioinformatics, research biologists and clinicians can use Pandomics to do OMICS data analytics and interpretation. In addition, pharmacological target discovery and biomarker development experts can use AI to generate powerful ideas and evaluate repositioning techniques.


In 2014, the business began developing a target identification engine. Since then, the technology has been proven through a number of successful collaborations with pharmaceutical firms and academic institutions, as well as the company’s own internal drug development projects. Pandemics aspires to be the go-to platform for all biologists and clinicians working with OMICS datasets, allowing them to more precisely categorize patient cohorts by swiftly analyzing, interpreting, and visualizing data.